repo-audit

Deep analysis of Git history: identify frequently changed hotspot files, analyze code ownership by contributor, and scan for leaked secrets. Triggered when users ask about Git analysis, code hotspots, who owns what code, secret scanning, security audits of commit history, or optimizing code review assignments.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, token-efficient tool skill with executable commands, real script references, and clean option tables. Its main gap is the absence of an audit-level workflow tying the three independent tools together with result-interpretation guidance.

Suggestions

Add a short "Running an audit" workflow that sequences the three tools (e.g. hotspots → ownership → secret scan) and explains how to interpret and combine their outputs.

Include one or two example invocations with sample output so Claude knows what to expect from each script.

Note that all three operations are read-only, so Claude can run them safely without a validation/rollback checkpoint.

Dimension	Reasoning	Score
Conciseness	Lean body that uses compact option tables and brief bullets, assuming Claude's competence; it does not explain what Git or secrets are, and every section earns its place.	3 / 3
Actionability	Gives executable invocations (e.g. `bash scripts/hotfiles.sh [options]`) with full option tables including defaults and output formats — copy-paste ready.	3 / 3
Workflow Clarity	Each tool's invocation is clear, but the skill is framed as a multi-dimensional "audit" yet provides no sequence for combining the three analyses and no guidance for interpreting or synthesizing results, leaving the audit-level workflow implicit.	2 / 3
Progressive Disclosure	SKILL.md is an overview that points to three real bundle scripts (hotfiles.sh, ownership.sh, secret-scan.sh) one level deep, with well-organized sections and clearly signaled usage blocks.	3 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that names three concrete capabilities and pairs them with an explicit, natural-language trigger clause covering the right user phrasings. It is concise yet complete with no fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "identify frequently changed hotspot files, analyze code ownership by contributor, and scan for leaked secrets" — rather than vague language.	3 / 3
Completeness	Explicitly answers both what (three-dimensional Git history analysis) and when ("Triggered when users ask about...") with an explicit trigger clause.	3 / 3
Trigger Term Quality	Covers natural terms users would say: "Git analysis, code hotspots, who owns what code, secret scanning, security audits of commit history, or optimizing code review assignments."	3 / 3
Distinctiveness Conflict Risk	Clear niche (Git history auditing) with distinct triggers unlikely to overlap with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: zebbern/claude-code-guide
Path: skills/repo-audit/SKILL.md
Commit: af7d491

Reviewed: about 7 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.